US-Egypt Cooperative Research: Machine Translation of Spoken Arabic into English

0001613 Levin描述：该奖项是为了支持宾夕法尼亚州匹兹堡卡内基梅隆大学（CMU）高级研究科学家洛里莱文博士和埃及开罗开罗大学计算机与信息学院Khaled Shaalan博士的合作项目。 科学家们计划开发一个系统，将阿拉伯语口语翻译成英语，法语，意大利语，德语和韩语，并将这些语言翻译成阿拉伯语。 翻译将仅限于有关旅行计划的句子（例如酒店和飞机预订）。 开发的系统将符合C-STAR联盟（语音翻译高级研究联盟）的要求，C-STAR联盟是一组在美国、法国、意大利、德国、日本和韩国相互合作的研究中心。 将阿拉伯语加入C-STAR系统将涉及三个技术组成部分：开发一种阿拉伯语语音识别器，它可以自动转录对着麦克风说的阿拉伯语句子;分析阿拉伯语句子的含义;从英语和其他语言输入句子的含义生成阿拉伯语句子。美国PI和埃及团队在这一研究领域拥有丰富的经验，并可以使用这项工作所需的主要研究设施。 CMU的科学家们在语言技术研究所（LTI）和交互系统实验室（ISL）一直致力于书面和口头语言的机器翻译。 他们最著名的翻译系统是书面语言的康德系统和口语的JANUS系统。 开罗大学的科学家们已经在自然语言处理（NLP）方面工作了十年，并为阿拉伯语开发了形态处理器，解析器和语法，还研究了英语到阿拉伯语的机器翻译。 这两所大学拥有互补的NLP组件和其他能力。 该提案符合INT的目标，即支持在共同感兴趣的领域进行合作研究。 该项目得到了美国-埃及联合基金方案的支持，该方案向两国的科学家和工程师提供赠款，以开展这些合作活动。

0001613LevinDescription: This award is to support a collaborative project by Dr. Lori Levin, Senior Research Scientist, Carnegie Mellon University (CMU), Pittsburgh, Pennsylvania and Dr. Khaled Shaalan, Faculty of Computer and Information, Cairo University, Cairo, Egypt. The scientists plan to develop a system for computer translation of spoken Arabic into English, French, Italian, German and Korean, and also for translation of these languages into Arabic. Translations will be limited to sentences about travel plans (e.g. hotel and plane reservations). The developed system will conform to the requirements of the C-STAR consortium (Consortium for Speech Translation Advanced Research) a group of research centers collaborating with each other in the United States, France, Italy, Germany, Japan, and Korea. Adding Arabic to the C-STAR system will involve three technological components: development of a Arabic speech recognizer which can automatically transcribe Arabic sentences that are spoken into a microphone; analysis of the meaning of Arabic sentences; generation of Arabic sentences from the meaning of input sentences in English and other languages.Scope: The US PI and the Egyptian teams have extensive experience in this area of research, and have access to major research facilities that are needed for this work. Scientists at CMU have been working on machine translation of written and spoken the language for fifteen years in the Language Technologies Institute (LTI) and the Interactive Systems Laboratory (ISL). Their most notable translation systems are the KANT system for written language and the JANUS system for spoken language. Scientists at Cairo University have been working on natural language processing (NLP) for ten years, and have produced a morphological processor, parser, and grammar for Arabic, and have also worked on English to Arabic machine translation. The two universities have complementary NLP components and other capabilities. This proposal meets the INT objective of supporting collaborative research in areas of mutual interest. This project is being supported under the US-Egypt Joint Fund Program, which provides grants to scientists and engineers in both countries to carry out these cooperative activities.